Sentiment Analysis of Hindi Reviews based on Negation and Discourse Relation
Namita Mittal, Basant Agarwal, Garvit Chouhan, Nitin Bania, Prateek Pareek · 2013
With recent developments in web technologies, percentage of web content in Hindi language is growing up at a lightning speed. Opinion classification research has gained tremendous momentum in recent times mostly for English language. However, there has been little work in this area for Indian languages. There is a need to analyse the Hindi language content and get insight of opinions expressed by people and various communities. In this paper, a method is proposed to increase the coverage of the Hindi SentiWordNet for better classification results. In addition to this, impact of the negation and discourse rules are investigated for Hindi sentiment analysis. Proposed algorithm produces 82.89% for positive reviews and 76.59 % for negative reviews, and an overall accuracy of 80.21%.